MultiObjective Optimization using Evolutionary Computation Techniques (original) (raw)
Multi-Objective Optimization Using Evolution Strategies
Facta universitatis. Series electronics and energetics, 2009
The present paper gives an overview of different versions of Evolution Strategies, namely the (1+1) Evolution Strategy, the Higher Order (μ/ρ, λ ) Evolu- tion Strategy and the Niching (κ(μ/ρ, λ)) Evolution Strategy, and how these meth- ods can be applied to problems in Electrical Engineering. Significant features of the algorithms implemented by the authors are presented. Finally, results are discussed on three electromagnetic optimization problems.
A hybrid multiobjective differential evolution method for electromagnetic device optimization
COMPEL: The International Journal for Computation and Mathematics in Electrical and Electronic Engineering, 2011
Purpose -The purpose of this paper is to show that the performance of differential evolution (DE) can be substantially improved by a combination of techniques. These enhancements are applicable to both single and multiobjective problems. Their combined use allows the optimization of complex 3D electromagnetic devices. Design/methodology/approach -DE is improved by a combination of techniques which are applied in a cascade way and their single and combined effect is tested on well-known benchmarks and domain-specific applications. Findings -It is shown that the combined use of enhancement techniques provides substantial improvements in the speed of convergence for both single and multiobjective problems.
IEEE Transactions on Magnetics, 2000
The differential evolution (DE) algorithm was initially developed for single-objective problems and was shown to be a fast, simple algorithm. In order to utilize these advantages in real-world problems it was adapted for multiobjective global optimization (MOGO) recently. In general multiobjective differential evolutionary algorithm, only use conventional DE strategies, and, in order to optimize performance constrains problems, the feasibility of the solutions was considered only at selection step. This paper presents a new multiobjective evolutionary algorithm based on differential evolution. In the mutation step, the proposed method which applied multiguiders instead of conventional base vector selection method is used. Therefore, feasibility of multiguiders, involving constraint optimization problems, is also considered. Furthermore, the approach also incorporates nondominated sorting method and secondary population for the nondominated solutions. The propose algorithm is compared with resent approaches of multiobjective optimizers in solving multiobjective version of Testing Electromagnetic Analysis Methods (TEAM) problem 22.
Electromagnetic device optimization by hybrid evolution strategy approaches
COMPEL: The International Journal for Computation and Mathematics in Electrical and Electronic Engineering, 2007
Purpose -This paper aims to show on a widely used benchmark problem that chaotic sequences can improve the search ability of evolution strategies (ES). Design/methodology/approach -The Lozi map is used to generate new individuals in the framework of ES algorithms. A quasi-Newton (QN) method is also used within the iterative loop to improve the solution's quality locally. Findings -It is shown that the combined use of chaotic sequences and QN methods can provide high-quality solutions with small standard deviation on the selected benchmark problem. Research limitations/implications -Although the benchmark is considered to be representative of typical electromagnetic problems, different test cases may give less satisfactory results. Practical implications -The proposed approach appears to be an efficient general purpose optimizer for electromagnetic design problems. Originality/value -This paper introduces the use of chaotic sequences in the area of electromagnetic design optimization.
Higher order evolution strategies for the global optimization of electromagnetic devices
IEEE Transactions on Magnetics, 1993
Abstmct -Basic evolution strategies @S) utilizing simplified features of biological evolution like mutation and selection are applied to solve problems of parameter identification for the optimal design of electromagnetic devices. Due to the fact that objective functions of real world applications usually have more than one minimum, additional features can be added to minimize the risk of getting trapped in a local minimum. Finite life span, recombination and population, applied in @/&) evolution strategies or a "disaster" with an unnatural high stepwidth after a certain number of generations can help to arrive at a reliable solution within a reasonable computational effort.
Multiobjective Optimization in Computational Electromagnetics
In this paper we show how multiobjective optimization can be applied to elec- tromagnetic problems. The optimization algorithms are combined with CAD and mesh generation software, and electromagnetic solvers. Three dieren t multiobjective optimization methods are applied: one evolutionary method, one method based on scalarizing of the objectives combined with a method for single objective optimization and a multiobjective respond surface method. To demonstrate the procedure we study the optimization of the return loss of a patch antennas at two dieren t frequencies.
Multiobjective Tabu Search Algorithms for Optimal Design of Electromagnetic Devices
IEEE Transactions on Magnetics, 2008
In this paper, an original algorithm to solve multiobjective optimization problems, which makes use of the tabu search meta-heuristic, is presented. Scalarization of the vector problem is performed by introducing fitness functions that take under control both the Pareto optimality of the solutions, and the uniformity in the Pareto front sampling. The performance of the proposed algorithm is compared with that of a scalar tabu search method, coupled with the -constraint strategy. The results on analytical and electromagnetic problems demonstrate the effectiveness of the method.
Niching genetic algorithms for optimization in electromagnetics. I. Fundamentals
IEEE Transactions on Magnetics, 1998
In this paper, we present a new approach for automatic design of electrodes. The investigated method consists in identifying an optimal shape from an optimal equipotential resulting from a system of point charges. The electric field and potential are computed using the point charge simulation method. Niching genetic algorithms and constrained optimization techniques are applied to the electrode benchmark in order to find multiple optimal profiles.
Genetic algorithm optimization applied to electromagnetics: a review
IEEE Transactions on Antennas and Propagation, 1997
Genetic algorithms are on the rise in electromagnetics as design tools and problem solvers because of their versatility and ability to optimize in complex multimodal search spaces. This paper describes the basic genetic algorithm and recounts its history in the electromagnetics literature. Also, the application of advanced genetic operators to the field of electromagnetics is described, and design results are presented for a number of different applications. Index Terms-Genetic algorithms. I. INTRODUCTION D URING the latter half of the nineteenth century, the biological sciences underwent a revolution when Charles Darwin discovered the processes by which nature selects and optimizes organizms fit for life [1]. About the same time, Gregor Mendel learned the basic laws of genetic inheritance which elucidate by what means evolution takes place [2]. The advent of computers and powerful computational techniques now enables us to apply Nature's optimization processes in the form of genetic algorithms (GA's) to devices built using Maxwell's equations. The objective functions that arise in electromagnetic optimization problems are often highly nonlinear, stiff, multiextremal, and nondifferentiable. In addition, they are almost always computationally expensive to evaluate. Historically, the vast majority of research efforts related to the design of electromagnetic systems using optimization methods has relied on deterministic optimization methods (DOM's) [3]. DOM's are known to have important drawbacks when applied to multiextremal and stiff optimization problems [4] and often lead to highly interactive and expensive design procedures. GA's (along with Monte Carlo techniques and simulated annealing) belong to a small but growing class of so-called global optimizers which are stochastic in nature and, therefore, less prone to converge to a weak local optimum than DOM's [5]-[10]. In various forms, GA's have been
IEEE Transactions on Magnetics, 2008
We describe a local search procedure for multiobjective genetic algorithms that employs quadratic approximations for all nonlinear functions involved in the optimization problem. The samples obtained by the algorithm during the evolutionary process are used to fit these quadratic approximations in the neighborhood of the point selected for local search, implying that no extra cost of function evaluations is required. After that, a locally improved solution is easily estimated from the associated quadratic problem. We demonstrate the hybridization of our procedure with the well-known multiobjective genetic algorithm. This methodology can also be coupled with other multiobjective evolutionary algorithms. The results show that the proposed procedure is suitable for time-demanding black-box optimization problems.
A new hybrid evolutionary algorithm for high dimension electromagnetic problems
2005
In this paper the authors present a new hybrid evolutionary algorithm, particularly suitable for high dimension electromagnetic problems. This method, called GSO, Genetical Swarm Optimization, essentially combines the features of other two well known evolutionary algorithms, the Genetic Algorithms and Particle Swarm Optimization.
Optimization of the electromagnetic devices using genetic algorithms method
2004
The present paper proposes and studies the efficiency of using a RSM enhanced ACO R algorithm for the optimization of electromagnetic devices. Different RSM methods, such as Box-Behnken, CCD and Doelhert, are applied to find most suitable parameters (optimal set) for the ACO R in order to solve the corresponding electromagnetic optimization problems. The parameters optimal set is found by building a metaheuristic function. In the same time, the optimal parameter set is searched and determined for each electromagnetic problems for different objective functions, the best and the average global best solution for a tests set. The electromagnetic devices to be optimized are the Loney's solenoid and an energy storage device, as defined by the TEAM22 problem. Both electromagnetic problems are proposed benchmarks from electromagnetic community.
IEEE Transactions on Magnetics, 2000
Real-world engineering optimization problems involve multiple design factors and constraints and consist in minimizing multiple noncommensurable and often competing objectives. In recent years, many evolutionary techniques for multiobjective optimization have been proposed. In this context, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) algorithm is an effective methodology to solve multiobjective optimization problems. A modified NSGA-II to seek the Pareto front of electromagnetic multiobjective design problems is proposed in this paper. We propose the use of chaotic sequences based on Zaslavskii map in the NSGA-II crossover operator. The proposed method is tested on TEAM 22 benchmark optimization problem with promising results.
Multiobjective Evolutionary Algorithms Applied to Microstrip
2009
This work presents three of the main evolutionary algorithms: Genetic Algorithm, Evolution Strategy and Evolutionary Programming, applied to microstrip antennas design. Efficiency tests were performed, considering the analysis of key physical and geometrical parameters, evolution type, numerical random generators effects, evolution operators and selection criteria. These algorithms were validated through design of microstrip antennas based on the Resonant Cavity Method, and allow multiobjective optimizations, considering bandwidth, standing wave ratio and relative material permittivity. The optimal results obtained with these optimization processes, were confirmed by CST Microwave Studio commercial package.
Distributed evolutionary algorithm for optimization in electromagnetics
IEEE Transactions on Magnetics, 2000
This paper presents a distributed universal evolutionary optimization environment designed for optimal design in electromagnetics. The optimizer can be tuned to act as a genetic algorithm or as an evolutionary strategy. Basic principles of optimizer design are discussed. The system is coded in Java and uses a remote method invocation technique to distribute computational tasks between local and/or remote servers. T.E.A.M Workshop problem 25 was used to estimate parallel performance of the system. An example of application is the optimal location of electrodes for electroconvulsive stimulation is presented.
COMPEL: The International Journal for Computation and Mathematics in Electrical and Electronic Engineering, 2009
Purpose -The purpose of this paper is to show, on a widely used benchmark problem, that adaptive mutation factors and attractive/repulsive phases guided by population diversity can improve the search ability of differential evolution (DE) algorithms. Design/methodology/approach -An adaptive mutation factor and attractive/repulsive phases guided by population diversity are used within the framework of DE algorithms. Findings -The paper shows that the combined use of adaptive mutation factors and population diversity in order to guide the attractive/repulsive behavior of DE algorithms can provide high-quality solutions with small standard deviation on the selected benchmark problem. Research limitations/implications -Although the chosen benchmark is considered to be representative of typical electromagnetic problems, different test cases may give less satisfactory results. Practical implications -The proposed approach appears to be an efficient general purpose stochastic optimizer for electromagnetic design problems. Originality/value -This paper introduces the use of population diversity in order to guide the attractive/repulsive behavior of DE algorithms.
IEEE Transactions on Magnetics, 2011
An effective methodology for a robust global optimization of electromagnetic devices is developed based on the gradient index and multi-objective optimization method. The method transforms a given optimization problem into a multi-objective optimization one by adding another optimization target for minimizing the gradient index. The performance and robustness of the obtained optimal designs from the proposed algorithm are investigated through a numerical experiment with the TEAM Workshop Problem 22.
A Multiobjective Gaussian Particle Swarm Approach Applied to Electromagnetic Optimization
IEEE Transactions on Magnetics, 2000
The development of optimization techniques for multiobjective problems in electromagnetics has been flourishing in the last decade. This paper proposes an improved multiobjective particle swarm optimization approach and applies it to the multiobjective version of TEAM workshop problem 22. Simulation results show that this improved version of the algorithm finds a better Pareto-optimal front with respect to more classical PSO methods while maintaining a better spread of nondominated solutions along the front. Furthermore, the proposed algorithm is compared with the widely used Nondominated Sorting Genetic Algorithm-II (NSGA-II) method highlighting a strongly different behaviour of these strategies.
A new hybrid technique for the optimization of large–domain electromagnetic problems
2005
The paper presents a new hybrid evolutionary algorithm suitable for the optimization of large-domain electromagnetic problems. The hybrid technique, called Genetical Swarm Optimization (GSO), combines Genetic Algorithms (GA) and Particle Swarm Optimization (PSO). GSO algorithm is modeled on the concepts of Darwin's theory based on natural selection and evolution, and on cultural and social rules derived from the swarm intelligence. Numerical results are presented for both mathematical and electromagnetic optimization problems.
IEEE Transactions on Magnetics, 1995
This paper compares the application of genetic algorithms and traditional gradient-based algorithms to various optimization problems in electromagnetics. Gradient algorithms work well for a small number of continuous parameters. Genetic algorithms are best for a large number of quantized parameters. gene1 1 1 1 0 1 0 0 0 1 Both antenna array and scattering optimization examples are gene2 1